Get a specific string - sql

It's my data and every ThroughRouteSid record has the same pattern.
six number and five comma. then I just want to get three and five
number into two record to template Table and get the same Count()
value to these two record.
For example: First record in the picture.
ThroughRouteSid(3730,2428,2428,3935,3935,3938,) Count(32).
I want a result like this:
2428 32 3935 32
I get What number I want.become two record and both have same Count value into template table

you can use XML to get your result, please refer below sample code -
create table #t1( ThroughRouteSid varchar(500) , Cnt int)
insert into #t1
select '3730,2428,2428,3935,3935,3938,' , len('3730,2428,2428,3935,3935,3938,')
union all select '1111,2222,3333,4444,5555,6666,' , len('1111,2222,3333,4444,5555,6666,')
select cast( '<xml><td>' + REPLACE( SUBSTRING(ThroughRouteSid ,1 , len(ThroughRouteSid)-1),',','</td><td>') + '</td></xml>' as xml) XmlData , Cnt
into #t2 from #t1
select XmlData.value('(xml/td)[3]' ,'int' ), Cnt ,XmlData.value('(xml/td)[5]' ,'int' ), Cnt
from #t2

First create the function referring How to Split a string by delimited char in SQL Server. Then try Querying the following
select (SELECT CONVERT(varchar,splitdata) + ' '+ Convert(varchar, [Count])+' ' FROM (select splitdata, ROW_NUMBER() over (ORDER BY (SELECT 100)) row_no
from [dbo].[fnSplitString](ThroughRouteSid,',')
where splitdata != '') as temp where row_no in (2,5)
for xml path('')) as col1 from [yourtable]

If you are using SQL Server 2016 you can do something like this:
create table #temp (ThroughRouteSid varchar(1024),[Count] int)
insert into #temp values
('3730,2428,2428,3935,3935,3938,',32),
('730,428,428,335,935,938,',28)
select
spt.value,
t.[Count]
from #temp t
cross apply (
select value from STRING_SPLIT(t.ThroughRouteSid,',') where LEN(value) > 0
)spt

Related

Generate a comma-separated list of numbers in a single string

Is there a way to generate a comma-separated string of a series of numbers where the "begin" and "end" numbers are provided?
For example, provide the numbers 1 and 10 and the output would be a single value of: 1,2,3,4,5,6,7,8,9,10
10/10/2019 edit explaining why I'm interested in this:
My workplace writes queries with several columns in the SELECT statement plus aggregate functions. Then a GROUP BY clause using the column numbers. I figured using a macro that creates a comma-separated list to copy/paste in would save some time.
SELECT t.colA
, t.colB
, t.colC
, t.colD
, t.colE
, t.colF
, t.colG
, t.colH
, t.colI
, t.colJ
, sum(t.colK) as sumK
, sum(t.colL) as sumL
, sum(t.colM) as sumM
FROM t
GROUP BY 1, 2, 3, 4, 5, 6, 7, 8, 9, 10
;
You can use a recursive CTE to generate your numbers, and xml_agg to generate your string:
with recursive nums (counter) as
( select * from (select cast(1 as bigint) as counter) t
union all
select
counter + 1
from nums
where counter between 1 and 9
)
select
trim(trailing ',' from cast(xmlagg(cast(counter as varchar(2)) || ',' order by counter) as varchar(100)))
from nums
Check these methods in SQL Server-
IF OBJECT_ID('TEMPDB..#Sample') IS NOT NULL
DROP TABLE #Sample
Create table #Sample
(
NUM int
)
declare #n int
select #n=10
insert into #Sample(NUM)
SELECT NUM FROM (select row_number() over (order by (select null)) AS NUM from sys.columns) A WHERE NUM<=#N
--Method 1 (For SQL SERVER -NEW VERSION Support)
SELECT STRING_AGG(NUM,',') AS EXPECTED_RESULT FROM #Sample
--Method 1 (For SQL SERVER -OLD VERSION Support)
select DISTINCT STUFF(CAST((
SELECT ' ,' +CAST(c.num AS VARCHAR(MAX))
FROM (
SELECT num
FROM #Sample
) c
FOR XML PATH(''), TYPE) AS VARCHAR(MAX)), 1, 2, '') AS EXPECTED_RESULT
from #Sample t
While loop seems appropriate
declare #begin int=1
declare #end int=11
declare #list varchar(500)
if #begin > #end
begin
select 'error, beginning number ' + convert(varchar(500),#begin)
+ ' must not be greater than ending number '
+ convert(varchar(500),#end) + '.' err
return
end
else
set #list = convert(varchar(500),#begin)
;
while #begin < #end
begin
set #begin += 1
set #list = #list + ',' + convert(varchar(500),#begin)
end
select #list
You might want to use varchar(5000) or something depending on how big you want it to get.
disclaimer -- I don't know if this works with teradata
I'm not sure there is a good direct way to generate a series in Teradata. You can fake it a few different ways though. Here's a comma separated list of numbers from 5 to 15, for example:
SELECT TRIM(TRAILING ',' FROM (XMLAGG(TRIM(rn)|| ',' ) (VARCHAR(10000))))
FROM (SELECT 4 + ROW_NUMBER() OVER (ORDER BY Sys_Calendar."CALENDAR".day_of_calendar) as rn FROM Sys_Calendar."CALENDAR" QUALIFY rn <= 15) t
I've only used sys_calendar.calendar here because it's a big table. Any big table would do here though.
Here's one way to do it in Teradata:
SELECT ARRAY_AGG(src.RowNum)
FROM (
SELECT ROW_NUMBER() OVER() AS RowNum
FROM sys_calendar.calendar
QUALIFY RowNum BETWEEN <begin_num> AND <end_num>
) src
This will give you the output as an ARRAY data type, which you can probably cast as a VARCHAR. It also assumes begin_num > 0 and <end_num> is less than the number of rows in the sys_calendar.calendar view. You can always fiddle with this to fit your required range of values.
There are also DelimitedBuild UDFs out there (if you can find one) that can be used to convert row values into delimited strings.
The cheapest way to achieve your goal is this one (no functions, or joins to tables required):
WITH RECURSIVE NumberRanges(TheNumber,TheString) AS
(
SELECT 1 AS TheNumber,casT(1 as VARCHAR(500)) as TheString
FROM
(
SELECT * FROM (SELECT NULL AS X) X
) DUMMYTABLE
UNION ALL
SELECT
TheNumber + 1 AS TheNumber,
TheString ||',' || TRIM(TheNumber+1)
FROM NumberRanges
WHERE
TheNumber < 10
)
SELECT TheString
FROM NumberRanges
QUALIFY ROW_NUMBER() OVER ( ORDER BY TheNumber DESC) = 1;
Result String: 1,2,3,4,5,6,7,8,9,10

Get unique values using STRING_AGG in SQL Server

The following query returns the results shown below:
SELECT
ProjectID, newID.value
FROM
[dbo].[Data] WITH(NOLOCK)
CROSS APPLY
STRING_SPLIT([bID],';') AS newID
WHERE
newID.value IN ('O95833', 'Q96NY7-2')
Results:
ProjectID value
---------------------
2 Q96NY7-2
2 O95833
2 O95833
2 Q96NY7-2
2 O95833
2 Q96NY7-2
4 Q96NY7-2
4 Q96NY7-2
Using the newly added STRING_AGG function (in SQL Server 2017) as it is shown in the following query I am able to get the result-set below.
SELECT
ProjectID,
STRING_AGG( newID.value, ',') WITHIN GROUP (ORDER BY newID.value) AS
NewField
FROM
[dbo].[Data] WITH(NOLOCK)
CROSS APPLY
STRING_SPLIT([bID],';') AS newID
WHERE
newID.value IN ('O95833', 'Q96NY7-2')
GROUP BY
ProjectID
ORDER BY
ProjectID
Results:
ProjectID NewField
-------------------------------------------------------------
2 O95833,O95833,O95833,Q96NY7-2,Q96NY7-2,Q96NY7-2
4 Q96NY7-2,Q96NY7-2
I would like my final output to have only unique elements as below:
ProjectID NewField
-------------------------------
2 O95833, Q96NY7-2
4 Q96NY7-2
Any suggestions about how to get this result? Please feel free to refine/redesign from scratch my query if needed.
Use the DISTINCT keyword in a subquery to remove duplicates before combining the results: SQL Fiddle
SELECT
ProjectID
,STRING_AGG(value, ',') WITHIN GROUP (ORDER BY value) AS
NewField
from (
select distinct ProjectId, newId.value
FROM [dbo].[Data] WITH(NOLOCK)
CROSS APPLY STRING_SPLIT([bID],';') AS newID
WHERE newID.value IN ( 'O95833' , 'Q96NY7-2' )
) x
GROUP BY ProjectID
ORDER BY ProjectID
You can use distinct in the subquery used for the apply:
SELECT d.ProjectID,
STRING_AGG( newID.value, ',') WITHIN GROUP (ORDER BY newID.value) AS
NewField
FROM [dbo].[Data] d CROSS APPLY
(select distinct value
from STRING_SPLIT(d.[bID], ';') AS newID
) newID
WHERE newID.value IN ( 'O95833' , 'Q96NY7-2' )
group by projectid;
This is a function that I wrote that answers the OP Title:
Improvements welcome!
CREATE OR ALTER FUNCTION [dbo].[fn_DistinctWords]
(
#String NVARCHAR(MAX)
)
RETURNS NVARCHAR(MAX)
WITH SCHEMABINDING
AS
BEGIN
DECLARE #Result NVARCHAR(MAX);
WITH MY_CTE AS ( SELECT Distinct(value) FROM STRING_SPLIT(#String, ' ') )
SELECT #Result = STRING_AGG(value, ' ') FROM MY_CTE
RETURN #Result
END
GO
Use like:
SELECT dbo.fn_DistinctWords('One Two Three Two One');
As #SeanLange pointed out in the comments, this is a terrible way to pull out the data, but if you had to, just make it 2 separate queries as follows:
SELECT
ProjectID
,STRING_AGG( val, ',') WITHIN GROUP (ORDER BY val) AS NewField
FROM
(
SELECT DISTINCT
ProjectID
,newID.value AS val
FROM
[dbo].[Data] WITH(NOLOCK)
CROSS APPLY STRING_SPLIT([bID],';') AS newID
WHERE
newID.value IN ('O95833' , 'Q96NY7-2')
) t
GROUP BY
ProjectID
That should do it.
Another possibility to get unique strings from STRING_AGG would be to perform these three steps after fetching the comma separated string:
Split the string (STRING_SPLIT)
Select DISTINCT from the splits
Apply STRING_AGG again to a select with a group on a single key
Example:
(select STRING_AGG(CAST(value as VARCHAR(MAX)), ',')
from (SELECT distinct 1 single_key, value
FROM STRING_SPLIT(STRING_AGG(CAST(customer_division as VARCHAR(MAX)), ','), ','))
q group by single_key) as customer_division
Here is my improvement on #ttugates to make it more generic:
CREATE OR ALTER FUNCTION [dbo].[fn_DistinctList]
(
#String NVARCHAR(MAX),
#Delimiter char(1)
)
RETURNS NVARCHAR(MAX)
WITH SCHEMABINDING
AS
BEGIN
DECLARE #Result NVARCHAR(MAX);
WITH MY_CTE AS ( SELECT Distinct(value) FROM STRING_SPLIT(#String,
#Delimiter) )
SELECT #Result = STRING_AGG(value, #Delimiter) FROM MY_CTE
RETURN #Result
END
You can make a distinct view of the table, that holds the aggregate values, that is even simpler:
Create Table Test (field1 varchar(1), field2 varchar(1));
go
Create View DistinctTest as (Select distinct field1, field2 from test group by field1,field2);
go
insert into Test Select 'A', '1';
insert into Test Select 'A', '2';
insert into Test Select 'A', '2';
insert into Test Select 'A', '2';
insert into Test Select 'D', '1';
insert into Test Select 'D', '1';
select string_agg(field1, ',') from Test where field2 = '1'; /* duplicates: A,D,D */;
select string_agg(field1, ',') from DistinctTest where field2 = '1'; /* no duplicates: A,D */;
Oracle (since version 19c) suports listagg (DISTINCT ..., but Microsoft SQL Server not probably.

how to extract a particular id from the string using sql

I want to extract a particular ids from the records in a table.For example i have a below table
Id stringvalue
1 test (ID 123) where another ID 2596
2 next ID145 and the condition I(ID 635,897,900)
I want the result set as below
ID SV
1 123,2596
2 145,635,897,900
i have tried the below query which extracts only one ID from the string:
Select Left(substring(string,PATINDEX('%[0-9]%',string),Len(string)),3) from Table1
I seriously don't encourage the T-SQL approach (as SQL is not meant to do this), however, a working version is presented below -
Try this
DECLARE #T TABLE(ID INT IDENTITY,StringValue VARCHAR(500))
INSERT INTO #T
SELECT 'test (ID 123) where another ID 2596' UNION ALL
SELECT 'next ID145 and the condition I(ID 635,897,900)'
;WITH SplitCTE AS(
SELECT
F1.ID,
X.SplitData
,Position = PATINDEX('%[0-9]%', X.SplitData)
FROM (
SELECT *,
CAST('<X>'+REPLACE(REPLACE(StringValue,' ',','),',','</X><X>')+'</X>' AS XML) AS XmlFilter
FROM #T F
)F1
CROSS APPLY
(
SELECT fdata.D.value('.','varchar(50)') AS SplitData
FROM f1.xmlfilter.nodes('X') AS fdata(D)) X
WHERE PATINDEX('%[0-9]%', X.SplitData) > 0),
numericCTE AS(
SELECT
ID
,AllNumeric = LEFT(SUBSTRING(SplitData, Position, LEN(SplitData)), PATINDEX('%[^0-9]%', SUBSTRING(SplitData, Position, LEN(SplitData)) + 't') - 1)
FROM SplitCTE
)
SELECT
ID
,STUFF(( SELECT ',' + c1.AllNumeric
FROM numericCTE c1
WHERE c1.ID = c2.ID
FOR XML PATH(''),TYPE)
.value('.','NVARCHAR(MAX)'),1,1,'') AS SV
FROM numericCTE c2
GROUP BY ID
/*
Result
ID SV
1 123,2596
2 145,635,897,900
*/
However, I completely agree with #Giorgi Nakeuri. It is better to use some programming language (if you have that at your disposal) and use regular expression for the same. You can figure out that, I have used REPLACE function two times, first to replace the blank space and second to replace the commas(,).
Hope you will get some idea to move on.

SQL Query for Min and Max Values [duplicate]

This question already has answers here:
How to split a comma-separated value to columns
(38 answers)
Closed 8 years ago.
I have the following data in a table. The number of values in each row can vary and the number of rows could also vary.
The table has 1 column with csv formatted values. The values will always be numeric
Data
1,2
4
5,12, 10
6,7,8,9,10
15,17
I would like to end up with a temp table with the following
Data Lowest Highest
1,2 1 2
4 4 4
5,12, 10 5 12
6,7,8,9,10 6 10
15,17 15 17
Can anyone help with writing a sql query or function to achieve this
Instead of function, you can achieve by this
;WITH tmp
AS (SELECT A.rn,split.a.value('.', 'VARCHAR(100)') AS String
FROM (SELECT Row_number() OVER(ORDER BY (SELECT NULL)) AS RN,
Cast ('<M>' + Replace([data], ',', '</M><M>') + '</M>' AS XML) AS String
FROM table1) AS A
CROSS apply string.nodes ('/M') AS Split(a))
SELECT X.data,Tmp.lower,Tmp.higher
FROM (SELECT rn,Min(Cast(string AS INT)) AS Lower,Max(Cast(string AS INT)) AS Higher
FROM tmp
GROUP BY rn) Tmp
JOIN (SELECT Row_number() OVER(ORDER BY (SELECT NULL)) AS RN1,data
FROM table1) X
ON X.rn1 = Tmp.rn
FIDDLE DEMO
Output would be:
Data Lower Higher
1,2 1 2
4 4 4
5,12, 10 5 12
6,7,8,9,10 6 10
15,17 15 17
First create a user defined function to convert each row of 'DATA' column to a intermediate table as:
/****** Object: UserDefinedFunction [dbo].[CSVToTable]******/
SET ANSI_NULLS ON
GO
SET QUOTED_IDENTIFIER ON
GO
CREATE FUNCTION [dbo].[CSVToTable] (#InStr VARCHAR(MAX))
RETURNS #TempTab TABLE
(id int not null)
AS
BEGIN
;-- Ensure input ends with comma
SET #InStr = REPLACE(#InStr + ',', ',,', ',')
DECLARE #SP INT
DECLARE #VALUE VARCHAR(1000)
WHILE PATINDEX('%,%', #INSTR ) <> 0
BEGIN
SELECT #SP = PATINDEX('%,%',#INSTR)
SELECT #VALUE = LEFT(#INSTR , #SP - 1)
SELECT #INSTR = STUFF(#INSTR, 1, #SP, '')
INSERT INTO #TempTab(id) VALUES (#VALUE)
END
RETURN
END
GO
Function is explained further here.
Then Using Cross Apply we can get the desired output as:
With CTE as
(
select
T.Data, Min(udf.Id) as [Lowest],Max(udf.Id) as [Highest]
from
Test T
CROSS APPLY dbo.CSVToTable(T.Data) udf
Group By Data
)
Select * from CTE
Sample Code here...
What a Cross Apply does is : it applies the right table expression to each row from the left table and produces a result table with the unified result sets.
Create table #temp1 (name varchar(100),value int )
Declare #len int
Select #len=(select max(LEN(name)-LEN(replace(name,',',''))) from table)
Declare #i int = 1
while (#i<=#len+1)
begin
insert into #temp1
select name,PARSENAME(REPLACE(name,',','.'),#i) from table t
set #i = #i+1
end
Select name,MIN(value) MINV,MAX(value) MAXV from #temp1 group by name
declare #Testdata table ( Data varchar(max))
insert #Testdata select '1,2'
insert #Testdata select '4'
insert #Testdata select '5,12, 10'
insert #Testdata select '6,7,8,9,10'
;with tmp( DataItem, Data, RN1) as (
select LEFT(Data, CHARINDEX(',',Data+',')-1),
STUFF(Data, 1, CHARINDEX(',',Data+','), ''),
ROW_NUMBER()OVER(ORDER BY (SELECT NULL))AS RN1
from #Testdata
union all
select LEFT(Data, CHARINDEX(',',Data+',')-1),
STUFF(Data, 1, CHARINDEX(',',Data+','), ''),RN1
from tmp
where Data > ''
)
Select x.data,t.Low,t.Up FROM
(Select RN1,MIN(Cast(DataItem AS INT)) As Low,
MAX(Cast(DataItem AS INT)) As Up
FROM tmp t GROUP BY t.RN1)t
JOIN (Select ROW_NUMBER()OVER(ORDER BY (SELECT NULL))AS RN,data from #Testdata)X
ON X.RN = t.RN1

Tricky SQL query requiring search for contains

I have data such as this:
Inventors column in my table
Hundley; Edward; Ana
Isler; Hunsberger
Hunsberger;Hundley
Names are separated by ;. I want to write a SQL query which sums up the count.
Eg. The result should be:
Hundley 2
Isler 1
Hunsberger 2
Edward 1
Ana 1
I could do a group by but this is not a simple group by as you can see. Any ideas/thoughts on how to get this output?
Edit: Changed results so it doesn't create any confusion that a row only contains 2 names.
You can take a look at this. I certainly do not recommend this way if you have lots of data, BUT you can do some modifications and use it and it works like a charm!
This is the new code for supporting unlimited splits:
Declare #Table Table (
Name Nvarchar(50)
);
Insert #Table (
Name
) Select 'Hundley; Edward; Anna'
Union Select 'Isler; Hunsberger'
Union Select 'Hunsberger; Hundley'
Union Select 'Anna'
;
With Result (
Part
, Remained
, [Index]
, Level
) As (
Select Case When CharIndex(';', Name, 1) = 0
Then Name
Else Left(Name, CharIndex(';', Name, 1) - 1)
End
, Right(Name, Len(Name) - CharIndex(';', Name, 1))
, CharIndex(';', Name, 1)
, 1
From #Table
Union All
Select LTrim(
Case When CharIndex(';', Remained, 1) = 0
Then Remained
Else Left(Remained, CharIndex(';', Remained, 1) - 1)
End
)
, Right(Remained, Len(Remained) - CharIndex(';', Remained, 1))
, CharIndex(';', Remained, 1)
, Level
+ 1
From Result
Where [Index] <> 0
) Select Part
, Count(*)
From Result
Group By Part
Cheers
;with cte as
(
select 1 as Item, 1 as Start, CHARINDEX(';',inventors, 1) as Split, Inventors from YourInventorsTable
union all
select cte.Item+1, cte.Split+1, nullif(CHARINDEX(';',inventors, cte.Split+1),0), inventors as Split
from cte
where cte.Split<>0
)
select rTRIM(lTRIM(SUBSTRING(inventors, start,isnull(split,len(inventors)+1)-start))), count(*)
from cte
group by rTRIM(lTRIM(SUBSTRING(inventors, start,isnull(split,len(inventors)+1)-start)))
You can create a split function to split the col values
select splittedValues.items,count(splittedValues) from table1
cross apply dbo.split(col1,';') splittedValues
group by splittedValues.items
DEMO in Sql fiddle
first make one function who take your comma or any other operator(;) separated string into one table and by using that temp table, apply GROUP function on that table.
So you will get count for separate value.
"select d.number,count(*) from (select number from dbo.CommaseparedListToTable('Hundley;Edward;Ana;Isler;Hunsberger;Hunsberger;Hundley',';'))d
group by d.number"
declare #text nvarchar(255) = 'Edward; Hundley; AnaIsler; Hunsberger; Hunsberger; Hundley ';
declare #table table(id int identity,name varchar(50));
while #text like '%;%'
Begin
insert into #table (name)
select SUBSTRING(#text,1,charindex(';',#text)-1)
set #text = SUBSTRING(#text, charindex(';',#text)+1,LEN(#text))
end
insert into #table (name)
select #text
select name , count(name ) counts from #table group by name
Output
name count
AnaIsler 1
Hundley 2
Hunsberger 2
Edward 1